Transfer learning algorithms have been widely studied for machine learning in recent times. In particular, in image recognition and classification tasks, transfer learning has shown significant benefits, and is getting plenty of attention in the research community. While performing a transfer of knowledge among source and target tasks, homogeneous dataset is not always available, and heterogeneous dataset can be chosen in certain circumstances. In this article, we propose a way of improving transfer learning efficiency, in case of a heterogeneous source and target, by using the Hebbian learning principle, called Hebbian transfer learning (HTL). In computer vision, biologically motivated approaches such as Hebbian learning represent associative learning, where simultaneous activation of brain cells positively affect the increase in synaptic connection strength between the individual cells. The discriminative nature of learning for the search of features in the task of image classification fits well to the techniques, such as the Hebbian learning rule—neurons that fire together wire together. The deep learning models, such as convolutional neural networks (CNN), are widely used for image classification. In transfer learning, for such models, the connection weights of the learned model should adapt to new target dataset with minimum effort. The discriminative learning rule, such as Hebbian learning, can improve performance of learning by quickly adapting to discriminate between different classes defined by target task. We apply the Hebbian principle as synaptic plasticity in transfer learning for classification of images using a heterogeneous source-target dataset, and compare results with the standard transfer learning case. Experimental results using CIFAR-10 (Canadian Institute for Advanced Research) and CIFAR-100 datasets with various combinations show that the proposed HTL algorithm can improve the performance of transfer learning, especially in the case of a heterogeneous source and target dataset.

Layered double hydroxides (LDHs) have gained vast importance as an electrocatalyst for water electrolysis to produce carbon-neutral and clean hydrogen energy. In this work, we demonstrated the fabrication of nano-flake-like NiMn LDH thin film electrodes onto porous membrane-like Ni-foam by using a simple and cost-effective electrodeposition method for oxygen evolution reaction (OER). Various Ni_1-xMn_x LDH (where x = 0.15, 0.25, 0.35, 0.50 and 0.75) thin film electrodes are utilized to achieve the optimal catalyst for an efficient and sustainable OER process. The various composition-dependent surface morphologies and porous-membrane-like structure provided the high electrochemical surface area along with abundant active sites facilitating the OER. The optimized catalyst referred to as Ni_0.65Mn_0.35 showed excellent OER properties with an ultralow overpotential of 253 mV at a current density of 50 mAcm⁻², which outperforms other state-of-the art catalysts reported in the literature. The relatively low Tafel slope of 130 mV dec⁻¹ indicates faster and more favorable reaction kinetics for OER. Moreover, Ni_0.65Mn_0.35 exhibits excellent durability over continuous operation of 20 h, indicating the great sustainability of the catalyst in an alkaline medium. This study provides knowledge for the fabrication and optimization of the OER catalyst electrode for water electrolysis.

Transfer learning is a deep learning technique has proved to be of great importance. However, most of the standard transfer learning algorithms are designed to repeat the same method for fine-tuning of the weights on the target domain. If we try to investigate the human brain's mechanism of learning a new complex concept based on a simple and basic concept, we can say, it is different from just the repetition of the same method of learning on a different dataset. In this article, we have introduced a novel transfer learning algorithm referred to as HTL (Hebbian transfer learning) using synaptic plasticity. The Hebbian theory, introduced by Donald Hebb, explains the "associative learning" in which the simultaneous activation of the brain cells positively affects the increase in the synaptic connection strength between the individual cells. This particular behaviour of Hebbian learning, makes it a very viable candidate for discriminative learning for the search of the specific feature for the task of object recognition or image classification. It helps connection weights of the learned model to adapt as per task dataset using numerical methods defining plasticity principles. Learning to discriminate between instances of different classes, over a variable number of classes within the dataset space defined by the task at hand, can be the result-oriented approach for classification problem. Extensive experiments verify that HTL, using synaptic plastic behaviour in heterogeneous transfer learning task does better than the standard state of the art methods of transfer learning on the cross-domain image classification task.

The plastic modifications in synaptic connectivity is primarily from changes triggered by neuromodulated dopamine signals. These activities are controlled by neuromodulation, which is itself under the control of the brain. The subjective brain’s self-modifying abilities play an essential role in learning and adaptation. The artificial neural networks with neuromodulated plasticity are used to implement transfer learning in the image classification domain. In particular, this has application in image detection, image segmentation, and transfer of learning parameters with significant results. This paper proposes a novel approach to enhance transfer learning accuracy in a heterogeneous source and target, using the neuromodulation of the Hebbian learning principle, called NDHTL (Neuromodulated Dopamine Hebbian Transfer Learning). Neuromodulation of plasticity offers a powerful new technique with applications in training neural networks implementing asymmetric backpropagation using Hebbian principles in transfer learning motivated CNNs (Convolutional neural networks). Biologically motivated concomitant learning, where connected brain cells activate positively, enhances the synaptic connection strength between the network neurons. Using the NDHTL algorithm, the percentage of change of the plasticity between the neurons of the CNN layer is directly managed by the dopamine signal’s value. The discriminative nature of transfer learning fits well with the technique. The learned model’s connection weights must adapt to unseen target datasets with the least cost and effort in transfer learning. Using distinctive learning principles such as dopamine Hebbian learning in transfer learning for asymmetric gradient weights update is a novel approach. The paper emphasizes the NDHTL algorithmic technique as synaptic plasticity controlled by dopamine signals in transfer learning to classify images using source-target datasets. The standard transfer learning using gradient backpropagation is a symmetric framework. Experimental results using CIFAR-10 and CIFAR-100 datasets show that the proposed NDHTL algorithm can enhance transfer learning efficiency compared to existing methods.